Publications by authors named "Y Amy Siu"
Improved Image Caption Rating - Datasets, Game, and Model.
Ext Abstr Hum Factors Computing Syst
April 2023
How well a caption fits an image can be difficult to assess due to the subjective nature of caption quality. What is a caption? We investigate this problem by focusing on image-caption ratings and by generating high quality datasets from human feedback with gamification. We validate the datasets by showing a higher level of inter-rater agreement, and by using them to train custom machine learning models to predict new ratings.
View Article and Find Full Text PDFBackground: Chronic kidney disease (CKD) requires accurate prediction of renal replacement therapy (RRT) initiation risk. This study developed deep learning algorithms (DLAs) to predict RRT risk in CKD patients by incorporating medical history and prescriptions in addition to biochemical investigations.
Methods: A multi-centre retrospective cohort study was conducted in three major hospitals in Hong Kong.
Article Synopsis
- University students face a high level of food insecurity, with over half of respondents (54%) reporting issues ranging from mild to severe food scarcity.
- Male students and those not living with parents are more at risk and are significantly engaged with campus food initiatives like the food pantry.
- Food-insecure students have poorer diet quality, scoring an average of 3.5 points lower than their food-secure peers, indicating a need for better university programs to enhance their nutritional intake.
Can environmental information disclosure spur corporate green innovation?
Sci Total Environ
February 2024
How can the disclosure of environmental information (EID) stimulate corporate green innovation (CGI)? This research challenges the prevailing assumption that environmental regulations impact CGI by influencing corporate compliance costs. Instead, it offers a fresh theoretical framework to explain how EID affects CGI. This study combines signal theory and resource dependence theory to develop a moderated mediation model, illustrating how EID reduces information asymmetry and alleviates corporate financial constraints (CFC).
View Article and Find Full Text PDFArticle Synopsis
- Carbon Intensity Constraint Policies (CICPs) in China aim to reduce carbon emissions but are variably effective due to local government interventions that sometimes hinder carbon emission performance (CEP).
- This study develops a new efficiency model to measure CEP across 30 provinces from 2002 to 2019, revealing that excessive government intervention negatively affects CEP, particularly under strong fiscal pressure.
- Findings suggest the need for a more balanced approach to government intervention in future CICPs to better meet environmental goals, including achieving peak carbon emissions by 2030 and carbon neutrality by 2060.